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

    Neuronpedia

    INDEX
    Explanations

    attack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OUGH
    -0.08
    вис
    -0.07
    ス
    -0.07
     Advocate
    -0.06
    ਸ
    -0.06
    accom
    -0.06
    区内
    -0.06
     constit
    -0.06
     LIC
    -0.06
    agrid
    -0.06
    POSITIVE LOGITS
    塄
    0.07
     đuổi
    0.07
     eyel
    0.07
     lí
    0.07
    뭥
    0.06
     repayment
    0.06
     ál
    0.06
    esc
    0.06
     doorway
    0.06
    (|
    0.06
    Act Density 0.032%

    No Known Activations