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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gregory
    -0.06
    unky
    -0.06
     Suicide
    -0.06
    incipal
    -0.06
     bitte
    -0.06
    教师
    -0.06
     scaling
    -0.06
     Samoa
    -0.06
    Sou
    -0.06
     polym
    -0.06
    POSITIVE LOGITS
    ToBounds
    0.07
    weekly
    0.06
     freel
    0.06
    羽
    0.06
    _payments
    0.06
    .Lines
    0.06
    _cl
    0.06
    Compilation
    0.06
    	for
    0.06
    AVAILABLE
    0.06
    Act Density 0.025%

    No Known Activations