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

    Neuronpedia

    INDEX
    Explanations

    say "opinions, cookies, decision" in the immediate vicinity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ex
    -0.07
     י
    -0.07
    ulations
    -0.07
     Ins
    -0.07
    亥
    -0.06
     ii
    -0.06
    ULO
    -0.06
    endoza
    -0.06
     GLint
    -0.06
    讶
    -0.06
    POSITIVE LOGITS
     residences
    0.08
     exhausting
    0.08
     Immun
    0.07
     singles
    0.07
    高速发展
    0.07
     optimistic
    0.07
     Susan
    0.07
    ống
    0.07
    _Static
    0.07
    遗传
    0.06
    Act Density 0.000%

    No Known Activations