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

    Neuronpedia

    INDEX
    Explanations

    unique hooks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    0.61
    as
    0.57
    src
    0.55
    ება
    0.52
    स्टर
    0.51
    relser
    0.50
    ok
    0.50
    ்களை
    0.50
    are
    0.49
    אים
    0.49
    POSITIVE LOGITS
     mediation
    0.47
     pharmaceutical
    0.45
     mediate
    0.45
     unsightly
    0.45
     scelta
    0.45
     vehicular
    0.44
     viser
    0.44
    🍷
    0.44
     경로
    0.43
     culinary
    0.43
    Act Density 0.000%

    No Known Activations