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

    Neuronpedia

    INDEX
    Explanations

    actually followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    //
    -1.64
    一些
    -1.54
    0
    -1.47
    }
    -1.38
     САД
    -1.36
     aprobación
    -1.34
    不要
    -1.34
    A
    -1.34
    زندگی
    -1.33
    /
    -1.33
    POSITIVE LOGITS
    ,’
    1.52
    </em>
    1.48
    altet
    1.45
    مزید
    1.35
    drav
    1.35
    軋
    1.34
    tricos
    1.34
     same
    1.32
     TAMBIÉN
    1.30
    سطس
    1.27
    Act Density 0.011%

    No Known Activations