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

    Neuronpedia

    INDEX
    Explanations

    Technical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sz
    -0.07
    ürü
    -0.06
    (machine
    -0.06
    矿物质
    -0.06
    (asset
    -0.06
     longitud
    -0.06
    �
    -0.06
    szą
    -0.06
     Slo
    -0.06
    ден
    -0.06
    POSITIVE LOGITS
    Net
    0.09
     borrowers
    0.07
     registering
    0.07
     UB
    0.07
     `\
    0.07
     النواب
    0.07
    حساب
    0.07
    ڕ
    0.07
     broadcasters
    0.07
    argv
    0.06
    Act Density 0.000%

    No Known Activations