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

    Neuronpedia

    INDEX
    Explanations

    logic and reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hai
    -0.07
     з
    -0.06
    сам
    -0.06
     genetics
    -0.06
     Lex
    -0.06
    ô
    -0.06
     seldom
    -0.06
     Behaviour
    -0.06
     نیست
    -0.06
    Certainly
    -0.06
    POSITIVE LOGITS
     uží
    0.07
    using
    0.06
    invoices
    0.06
    กร
    0.06
     scrollView
    0.06
    均
    0.06
     viewer
    0.06
     streamline
    0.06
    契
    0.06
     mary
    0.06
    Act Density 0.021%

    No Known Activations