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

    Neuronpedia

    INDEX
    Explanations

    mathematical reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ham
    -0.08
    Ham
    -0.08
    ારા
    -0.08
    =text
    -0.08
     eftir
    -0.08
     છોડ
    -0.08
     imme
    -0.07
    γω
    -0.07
     Hamlet
    -0.07
    werkings
    -0.07
    POSITIVE LOGITS
    Validity
    0.09
    Constraints
    0.09
    是否合法
    0.08
     подходит
    0.08
     feasibility
    0.08
     Constraints
    0.08
     gült
    0.08
     constraints
    0.08
     Check
    0.08
     überprü
    0.08
    Act Density 0.063%

    No Known Activations