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

    Neuronpedia

    INDEX
    Explanations

    organizational/institutional contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Student
    -0.08
     mastur
    -0.08
    🎁
    -0.08
     masturbation
    -0.07
    おそらく
    -0.07
    路人
    -0.07
     masturb
    -0.07
     stddev
    -0.07
     различных
    -0.07
    ģ
    -0.06
    POSITIVE LOGITS
     saying
    0.08
    tile
    0.07
     olive
    0.07
    聲音
    0.07
    鲴
    0.06
     located
    0.06
    やり
    0.06
    ບ
    0.06
     Colt
    0.06
     affiliation
    0.06
    Act Density 0.089%

    No Known Activations