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

    Neuronpedia

    INDEX
    Explanations

    lens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Level
    -0.07
    Pr
    -0.06
     організ
    -0.06
     swinger
    -0.06
     hypo
    -0.06
    ━━
    -0.06
    ğe
    -0.06
    Erot
    -0.06
    Pot
    -0.06
    かない
    -0.06
    POSITIVE LOGITS
    )object
    0.06
     thin
    0.06
     Mutex
    0.06
    forum
    0.06
     gson
    0.06
     Static
    0.06
    AMILY
    0.06
     numeral
    0.06
    VARCHAR
    0.06
    -supported
    0.06
    Act Density 0.002%

    No Known Activations