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

    Neuronpedia

    INDEX
    Explanations

    sports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    warf
    -0.08
     ポ
    -0.08
     Chicken
    -0.07
    ична
    -0.07
    MOOTH
    -0.06
     Worship
    -0.06
     schemes
    -0.06
     Dane
    -0.06
    ############
    -0.06
     stringBy
    -0.06
    POSITIVE LOGITS
    ับผ
    0.06
    .Level
    0.06
    Transaction
    0.06
    ็ค
    0.06
    åde
    0.06
     distinctly
    0.06
     teasing
    0.05
     compliments
    0.05
     instantiated
    0.05
    mans
    0.05
    Act Density 0.025%

    No Known Activations