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

    Neuronpedia

    INDEX
    Explanations

    conversational openers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     schließlich
    0.34
    茎
    0.33
     zudem
    0.32
    here
    0.31
    श्न
    0.31
    usammen
    0.31
    SEQU
    0.31
    стное
    0.31
     distante
    0.31
    ipps
    0.31
    POSITIVE LOGITS
    nabi
    0.39
     openly
    0.35
    anjing
    0.35
    naz
    0.33
     violated
    0.32
    ナイ
    0.32
    oporto
    0.32
    emoration
    0.32
     communications
    0.31
     enclosed
    0.31
    Act Density 0.000%

    No Known Activations