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

    Neuronpedia

    INDEX
    Explanations

    someone else

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    奥地利
    -0.07
    achusetts
    -0.07
     encounters
    -0.07
    =localhost
    -0.07
     softened
    -0.07
     Juliet
    -0.07
    ঔ
    -0.06
     dou
    -0.06
    .JPanel
    -0.06
    _pow
    -0.06
    POSITIVE LOGITS
    0.07
    _DT
    0.07
    雇佣
    0.07
     인정
    0.07
    рма
    0.07
    هجوم
    0.07
    Insets
    0.07
    崇拜
    0.07
    LOGY
    0.06
    _agent
    0.06
    Act Density 0.085%

    No Known Activations