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

    Neuronpedia

    INDEX
    Explanations

    them

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -su
    -0.07
    فال
    -0.07
     learned
    -0.07
    专卖
    -0.07
     revel
    -0.07
    当初
    -0.06
    켚
    -0.06
     learning
    -0.06
    .po
    -0.06
     tre
    -0.06
    POSITIVE LOGITS
    ANDOM
    0.07
    enzyme
    0.07
     Terraria
    0.07
    primer
    0.06
    UY
    0.06
    beat
    0.06
    .gwt
    0.06
    _BAND
    0.06
    基金管理
    0.06
    _mux
    0.06
    Act Density 0.030%

    No Known Activations