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

    Neuronpedia

    INDEX
    Explanations

    Steroids and side effects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     actuator
    -0.08
     Wim
    -0.08
    Conn
    -0.08
    .Pull
    -0.08
    -0.07
     Entrance
    -0.07
     calibr
    -0.07
     adelante
    -0.07
    Connection
    -0.07
    控
    -0.07
    POSITIVE LOGITS
    న్న
    0.08
    _original
    0.08
     exercícios
    0.08
     բ
    0.08
     zend
    0.08
     గా
    0.08
    usform
    0.08
     באמת
    0.08
    بن
    0.07
     מענ
    0.07
    Act Density 0.007%
    No Known Activations