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

    Neuronpedia

    INDEX
    Explanations

    leaving or beyond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     भावनाओं
    0.60
    パーティ
    0.52
     acompañada
    0.52
     obiettivo
    0.52
    每
    0.51
    ാ
    0.50
    руп
    0.48
     Aquí
    0.48
     そう
    0.48
     idées
    0.48
    POSITIVE LOGITS
    l
    0.62
    n
    0.57
    c
    0.51
    h
    0.49
    scape
    0.47
    s
    0.46
    gana
    0.46
    thon
    0.45
     Parkway
    0.45
    ;
    0.45
    Act Density 0.000%

    No Known Activations