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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    —for
    -0.07
    ثیر
    -0.07
    additional
    -0.06
     intel
    -0.06
     stif
    -0.06
     refresh
    -0.06
    َى
    -0.06
    :
↵
↵
    -0.06
    [text
    -0.06
    "For
    -0.06
    POSITIVE LOGITS
    ()");↵
    0.08
    pmat
    0.07
    .getMessage
    0.07
     득
    0.06
    лені
    0.06
    енти
    0.06
     �
    0.06
    аци
    0.06
     مول
    0.06
    олос
    0.06
    Act Density 0.168%

    No Known Activations