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

    Neuronpedia

    INDEX
    Explanations

    Voting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    someone
    -0.07
    怕
    -0.07
     외
    -0.07
    .slide
    -0.06
    something
    -0.06
    acz
    -0.06
    middlewares
    -0.06
    duction
    -0.06
    enstein
    -0.06
    .way
    -0.06
    POSITIVE LOGITS
    휴
    0.06
     [][]
    0.06
    _TRI
    0.06
    184
    0.06
    езда
    0.06
     درد
    0.06
     Brom
    0.06
     FALL
    0.06
     meta
    0.06
     nạn
    0.06
    Act Density 0.027%

    No Known Activations