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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HV
    -0.06
    
    -0.06
    …)
    -0.06
     Miy
    -0.06
    しか
    -0.06
    идент
    -0.06
     coef
    -0.06
    นวน
    -0.06
     hå
    -0.06
    elerinden
    -0.06
    POSITIVE LOGITS
     harmony
    0.07
     httpClient
    0.07
     Crack
    0.07
    ุธ
    0.06
     ---
    0.06
    _connected
    0.06
    duto
    0.06
    анти
    0.06
    onor
    0.06
    .backend
    0.06
    Act Density 0.001%

    No Known Activations