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

    Neuronpedia

    INDEX
    Explanations

    HT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     περι
    -0.07
     Pemb
    -0.07
     aussi
    -0.07
     accurate
    -0.07
     PRI
    -0.06
    基
    -0.06
     pemb
    -0.06
     anomal
    -0.06
     приб
    -0.06
     Benz
    -0.06
    POSITIVE LOGITS
    HT
    0.16
     HT
    0.14
    ht
    0.12
     ht
    0.11
    (ht
    0.09
     hf
    0.08
    hta
    0.08
    TY
    0.08
     Hit
    0.08
    _HT
    0.08
    Act Density 0.003%

    No Known Activations