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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SW
    -0.07
    has
    -0.07
    dictions
    -0.07
    ันน
    -0.07
    Destructor
    -0.07
    itar
    -0.07
    ิช
    -0.06
    âu
    -0.06
     kinetics
    -0.06
    asto
    -0.06
    POSITIVE LOGITS
    //--------------------------------------------------------------↵
    0.07
     });
↵
    0.07
     kdyby
    0.06
     staunch
    0.06
    .lineWidth
    0.06
     तरफ
    0.06
    .prot
    0.06
     सफ
    0.06
    ize
    0.06
     万元
    0.06
    Act Density 0.077%

    No Known Activations