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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    implicitly
    -0.08
    📋
    -0.07
     סו
    -0.06
     Orientation
    -0.06
     gradual
    -0.06
     vaguely
    -0.06
     deline
    -0.06
    Founded
    -0.06
    湟
    -0.06
    _lv
    -0.06
    POSITIVE LOGITS
    _EVENT
    0.07
    任何
    0.07
    节点
    0.07
     switch
    0.07
     vida
    0.07
    osal
    0.07
    .agent
    0.07
    _mgr
    0.07
    react
    0.07
     üretim
    0.07
    Act Density 0.005%

    No Known Activations