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

    Neuronpedia

    INDEX
    Explanations

    warming fashion policies data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gu
    0.39
    tStart
    0.39
    절
    0.37
     substitution
    0.37
    Референ
    0.37
     homolog
    0.37
    Substituting
    0.37
    Substitution
    0.37
     binh
    0.37
     Cahill
    0.36
    POSITIVE LOGITS
     meningkat
    0.39
    rägen
    0.38
    -(
    0.37
     аппарат
    0.36
     mr
    0.36
    Department
    0.36
    Mr
    0.36
     -(
    0.36
    ラック
    0.36
    ratos
    0.35
    Act Density 0.000%

    No Known Activations