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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ip
    -0.07
    animal
    -0.07
    озі
    -0.06
    ckill
    -0.06
    ότε
    -0.06
    .setPassword
    -0.06
     Im
    -0.06
     supremacist
    -0.06
    出す
    -0.06
    .sim
    -0.06
    POSITIVE LOGITS
    (${
    0.06
     poprvé
    0.06
    ilogue
    0.06
    驾
    0.06
    ，或
    0.06
    �i
    0.06
    (attribute
    0.06
    -то
    0.06
    connector
    0.06
     Marshall
    0.05
    Act Density 0.205%

    No Known Activations