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

    Neuronpedia

    INDEX
    Explanations

    Code/data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nunca
    -0.07
    nu
    -0.07
    "net
    -0.07
    -ad
    -0.07
    浴
    -0.07
     altijd
    -0.07
    ぅ
    -0.07
    nd
    -0.06
     NT
    -0.06
     ansch
    -0.06
    POSITIVE LOGITS
    082
    0.07
     مال
    0.07
     Estr
    0.07
    017
    0.07
    olina
    0.07
    BorderColor
    0.06
    032
    0.06
    056
    0.06
    \Block
    0.06
    092
    0.06
    Act Density 0.040%

    No Known Activations