Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    elements or phrases that involve parenthetical statements and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text within parentheses

    np_acts-logits-general · gemini-2.0-flash

    technical terms and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ).
    -1.41
    ].
    -1.34
    ».
    -1.31
    }.
    -1.25
    .
    -1.24
    。
    -1.22
    ".
    -1.19
    .
    -1.16
    }$.
    -1.11
    \}.
    -1.10
    POSITIVE LOGITS
     &___
    0.93
    rungsseite
    0.92
    WithMany
    0.89
    transQ
    0.88
     unknownFields
    0.86
    adaptiveStyles
    0.85
    IndentedString
    0.83
     ArrayAdapter
    0.81
    __(/*!
    0.81
    apunov
    0.81
    Act Density 0.401%

    No Known Activations