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

    Neuronpedia

    INDEX
    Explanations

    manage bot commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Column
    0.41
     columna
    0.39
     Lean
    0.39
     avanzando
    0.39
     পূর্ববাংলা
    0.37
     exact
    0.37
     vjer
    0.36
     süt
    0.36
     mascot
    0.36
     column
    0.35
    POSITIVE LOGITS
    toprule
    0.45
    RULE
    0.42
    ALAR
    0.42
    rule
    0.42
    Ronald
    0.41
    jö
    0.40
    Gross
    0.40
    ോഷ
    0.40
     jurisdictional
    0.40
    အတွက်
    0.39
    Act Density 0.001%

    No Known Activations