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

    Neuronpedia

    INDEX
    Explanations

    asking and reacting to her

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vijf
    0.38
     fünf
    0.37
     forty
    0.37
     infe
    0.35
     sechs
    0.35
     zehn
    0.35
     defraud
    0.35
     coleta
    0.35
     incremento
    0.35
     eup
    0.34
    POSITIVE LOGITS
    läss
    0.41
    roidism
    0.38
    ⚠️
    0.37
    Quartz
    0.37
    sik
    0.37
    intă
    0.37
    当你
    0.37
    andır
    0.37
     असतात
    0.36
    𖤐
    0.36
    Act Density 0.083%

    No Known Activations