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

    Neuronpedia

    INDEX
    Explanations

    initiating a step or instruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вки
    0.61
    ش
    0.53
    resión
    0.52
    ның
    0.50
    ন
    0.49
    ơi
    0.47
     Espí
    0.47
    roir
    0.47
    lán
    0.46
    賊
    0.45
    POSITIVE LOGITS
     philosophers
    0.55
     אחר
    0.48
     monotonic
    0.47
     ingin
    0.46
     marketers
    0.46
     classifier
    0.46
     mM
    0.46
     nit
    0.46
     fl
    0.45
     个
    0.45
    Act Density 0.000%

    No Known Activations