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

    Neuronpedia

    INDEX
    Explanations

    conditional phrasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scales
    0.80
     schme
    0.79
    ests
    0.77
     mouthful
    0.75
    stage
    0.73
    ständ
    0.71
    roots
    0.71
     claws
    0.71
    )?
    0.71
    лан
    0.71
    POSITIVE LOGITS
    ون
    0.93
     arrivée
    0.86
    و
    0.86
     obiettivo
    0.82
     objectif
    0.80
    ۣ
    0.80
     东
    0.80
    㓈
    0.79
     intervento
    0.78
     Consultado
    0.77
    Act Density 0.001%

    No Known Activations