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

    Neuronpedia

    INDEX
    Explanations

    say "s word"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intens
    -0.07
    .metroLabel
    -0.07
     intim
    -0.07
     StringUtils
    -0.07
    _beh
    -0.06
    laus
    -0.06
     mav
    -0.06
    .tipo
    -0.06
     kwargs
    -0.06
     predicates
    -0.06
    POSITIVE LOGITS
    _registry
    0.07
     Babies
    0.07
    ired
    0.06
     Moo
    0.06
    (`↵
    0.06
     वजह
    0.06
    Opp
    0.06
     UITapGestureRecognizer
    0.06
    910
    0.06
    ickle
    0.06
    Act Density 0.005%

    No Known Activations