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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical models and graph structures

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

    Code snippets containing bracketed expressions

    np_acts-logits-general · gemini-2.0-flash

    SMR assumptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pollock
    -0.60
    я
    -0.59
    ICIA
    -0.59
    aic
    -0.57
    صه
    -0.57
    a
    -0.56
    ICED
    -0.55
    ense
    -0.54
     Jacobson
    -0.54
     Adamson
    -0.54
    POSITIVE LOGITS
    erir
    0.63
    rr
    0.62
    rrrr
    0.59
    }$​
    0.58
    SpringRunner
    0.58
    rrr
    0.57
    r
    0.57
    ror
    0.56
    er
    0.56
    rrrrrr
    0.55
    Act Density 0.844%

    No Known Activations