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

    Neuronpedia

    INDEX
    Explanations

    code templates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atham
    -0.07
    decor
    -0.06
     Fool
    -0.06
    oS
    -0.06
     withheld
    -0.06
    Echo
    -0.06
    /watch
    -0.06
     �
    -0.06
    Body
    -0.06
     cooker
    -0.06
    POSITIVE LOGITS
     рассчит
    0.07
     tennis
    0.07
    igte
    0.06
    maps
    0.06
    _areas
    0.06
     февра
    0.06
     {}
    0.06
    .addButton
    0.06
     unas
    0.06
     bombard
    0.06
    Act Density 0.017%

    No Known Activations