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

    Neuronpedia

    INDEX
    Explanations

    html/xml tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    -1.76
     also
    -1.71
     in
    -1.58
     at
    -1.55
     or
    -1.54
     as
    -1.52
     but
    -1.52
     with
    -1.46
    :
    -1.38
     if
    -1.32
    POSITIVE LOGITS
    樒
    1.40
     pegatinas
    1.38
     zoude
    1.37
    ajout
    1.36
    昔から
    1.35
     étan
    1.32
    1.32
     soddis
    1.32
    螃
    1.31
    affichage
    1.30
    Act Density 0.012%

    No Known Activations