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

    Neuronpedia

    INDEX
    Explanations

    Excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ре
    -0.07
    _drag
    -0.06
     needles
    -0.06
    Merit
    -0.06
    peat
    -0.06
    .codec
    -0.06
    Nintendo
    -0.06
    UserDefaults
    -0.06
     Actor
    -0.06
    ところ
    -0.06
    POSITIVE LOGITS
    errupt
    0.07
     experimented
    0.07
    elle
    0.07
     ekonom
    0.06
     ontvangst
    0.06
    avy
    0.06
    -aligned
    0.06
     may
    0.06
     carrier
    0.06
     soğuk
    0.06
    Act Density 0.000%

    No Known Activations