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

    Neuronpedia

    INDEX
    Explanations

    improvements/feedback

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rig
    -0.07
    .Restrict
    -0.06
     zahl
    -0.06
    _decoder
    -0.06
    ैप
    -0.06
    ct
    -0.06
     zug
    -0.06
    findOne
    -0.06
     MOR
    -0.06
     principles
    -0.06
    POSITIVE LOGITS
    -columns
    0.07
    .ps
    0.07
    以后
    0.07
     viewed
    0.07
    の子
    0.07
    共和
    0.07
    aley
    0.06
     UIView
    0.06
     siguiente
    0.06
    ija
    0.06
    Act Density 0.035%

    No Known Activations