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

    Neuronpedia

    INDEX
    Explanations

    helping answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    話
    -0.07
    "encoding
    -0.07
     بار
    -0.06
     academia
    -0.06
     teenage
    -0.06
     Assign
    -0.06
     önce
    -0.06
     кноп
    -0.06
    НІ
    -0.06
    .Ar
    -0.06
    POSITIVE LOGITS
     fascinating
    0.06
    lashes
    0.06
    loops
    0.06
    plitude
    0.06
    CAA
    0.06
    盟
    0.06
    abi
    0.06
     sniper
    0.06
    eldorf
    0.06
     neu
    0.06
    Act Density 0.062%

    No Known Activations