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

    Neuronpedia

    INDEX
    Explanations

    would

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Apt
    -0.07
    ゅ
    -0.06
    ':↵
    -0.06
    mers
    -0.06
     DropIndex
    -0.06
     astronaut
    -0.06
    ographers
    -0.06
     Unsupported
    -0.06
     Rape
    -0.06
     vog
    -0.06
    POSITIVE LOGITS
    Remove
    0.07
     rè
    0.07
    _PD
    0.07
    .Import
    0.07
    (resource
    0.06
    Ljava
    0.06
    рии
    0.06
    Invoke
    0.06
    ROID
    0.06
    ofilm
    0.06
    Act Density 0.000%

    No Known Activations