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

    Neuronpedia

    INDEX
    Explanations

    we've

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ாத
    -0.08
     getting
    -0.08
    -0.08
    ्ता
    -0.08
     gets
    -0.08
    որդ
    -0.07
     pregnancy
    -0.07
     gampang
    -0.07
    Preg
    -0.07
    ја
    -0.07
    POSITIVE LOGITS
    Widgets
    0.08
     castles
    0.08
    .house
    0.07
    /colors
    0.07
     psychologists
    0.07
    )=>
    0.07
    Scientists
    0.07
    led
    0.07
    ACH
    0.07
    HIP
    0.07
    Act Density 0.001%
    No Known Activations