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

    Neuronpedia

    INDEX
    Explanations

    possibility/alternatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Zy
    -0.06
    .Equals
    -0.06
     дых
    -0.05
     Hansen
    -0.05
    .f
    -0.05
    .dm
    -0.05
    wu
    -0.05
     KeyValue
    -0.05
     elastic
    -0.05
    {{$
    -0.05
    POSITIVE LOGITS
    NESS
    0.07
    าหล
    0.07
    existence
    0.07
    ezpe
    0.07
    ＝＝
    0.07
    NE
    0.06
    \Service
    0.06
    ไซต
    0.06
    θηκαν
    0.06
    graded
    0.06
    Act Density 0.039%

    No Known Activations