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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cade
    -0.07
     Rut
    -0.06
     �
    -0.06
     Messi
    -0.06
    ilege
    -0.06
    優
    -0.06
     yüzyıl
    -0.06
     预
    -0.06
    -corner
    -0.06
    هرست
    -0.06
    POSITIVE LOGITS
    .destroy
    0.07
    ophobia
    0.06
    \Application
    0.06
     nächsten
    0.06
     actresses
    0.06
    <translation
    0.06
    -linear
    0.06
     lu
    0.06
     επα
    0.06
    techn
    0.06
    Act Density 0.025%

    No Known Activations