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

    Neuronpedia

    INDEX
    Explanations

    off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tipped
    -0.06
    četně
    -0.06
    lep
    -0.06
     detal
    -0.06
    iguiente
    -0.06
     opposing
    -0.06
     【
    -0.06
    �果
    -0.06
     virtues
    -0.06
     sideline
    -0.06
    POSITIVE LOGITS
    .b
    0.08
    َد
    0.07
    鉄
    0.06
     NSA
    0.06
    MASTER
    0.06
     auditor
    0.06
    #w
    0.06
     maze
    0.06
     american
    0.06
    ãeste
    0.06
    Act Density 0.000%

    No Known Activations