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

    Neuronpedia

    INDEX
    Explanations

    MessageBox show functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Whether
    0.45
     probable
    0.43
    LOP
    0.42
     Patrick
    0.41
     Chile
    0.41
    oteric
    0.41
     போர்
    0.41
     Decode
    0.41
     সৌম
    0.40
     এটির
    0.40
    POSITIVE LOGITS
    xer
    0.40
     заку
    0.37
    Blur
    0.36
    ｽ
    0.36
    स्प
    0.36
     flexing
    0.35
    頼
    0.34
     clones
    0.32
    沭
    0.32
     complic
    0.32
    Act Density 0.000%

    No Known Activations