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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nw
    -0.07
    стре
    -0.07
    Explorer
    -0.07
    prod
    -0.07
    /default
    -0.06
    _hw
    -0.06
    247
    -0.06
    _Bl
    -0.06
    proj
    -0.06
    loc
    -0.06
    POSITIVE LOGITS
    وسی
    0.06
     incons
    0.06
    汗
    0.06
    _good
    0.06
     Ledger
    0.05
    Keeper
    0.05
     Pipe
    0.05
    Millis
    0.05
    _CHANGED
    0.05
    ♥
    0.05
    Act Density 0.057%

    No Known Activations