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

    Neuronpedia

    INDEX
    Explanations

    HTML image borders / alignment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Property
    -0.08
    Leave
    -0.08
     Playboy
    -0.07
    续约
    -0.07
    _manager
    -0.07
    �认
    -0.07
     honeymoon
    -0.07
     Further
    -0.07
    orsch
    -0.07
     Bakanı
    -0.07
    POSITIVE LOGITS
     metric
    0.07
     neutral
    0.06
    깞
    0.06
    ABLE
    0.06
     rand
    0.06
     filt
    0.06
    _SID
    0.06
     baff
    0.06
     ech
    0.06
    ％
    0.06
    Act Density 0.016%

    No Known Activations