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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ４
    -0.07
    ْت
    -0.07
    oj
    -0.06
    .ch
    -0.06
    	entry
    -0.06
    	typ
    -0.06
     Hayden
    -0.06
    ご
    -0.06
    �
    -0.06
     όπως
    -0.06
    POSITIVE LOGITS
     Subset
    0.08
     MATCH
    0.07
     catal
    0.06
     binds
    0.06
    achs
    0.06
    Know
    0.06
     toll
    0.06
    .Condition
    0.06
    _INS
    0.06
    .Screen
    0.06
    Act Density 0.051%

    No Known Activations