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

    Neuronpedia

    INDEX
    Explanations

    updates and new information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    airport
    -0.06
     polite
    -0.06
    >X
    -0.06
     continues
    -0.06
     abolition
    -0.06
     volatility
    -0.06
    'C
    -0.06
     marsh
    -0.06
    .GetResponse
    -0.06
    bower
    -0.06
    POSITIVE LOGITS
     væ
    0.07
    케
    0.07
    TextInput
    0.07
     navbar
    0.06
     nhớ
    0.06
    แต
    0.06
     elektronik
    0.06
    fsp
    0.06
    _AT
    0.06
     DSP
    0.06
    Act Density 0.017%

    No Known Activations