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

    Neuronpedia

    INDEX
    Explanations

    skill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lists
    -0.07
    /lists
    -0.07
    FAILED
    -0.06
    eof
    -0.06
     Lies
    -0.06
    <J
    -0.06
    )});↵
    -0.06
    /p
    -0.06
    ");↵↵↵
    -0.06
     Printing
    -0.06
    POSITIVE LOGITS
     ExecutionContext
    0.07
    -central
    0.07
     inflatable
    0.06
    ское
    0.06
    Unused
    0.06
    .Fl
    0.06
     strav
    0.06
    ture
    0.06
    imiento
    0.06
    _oc
    0.06
    Act Density 0.012%

    No Known Activations