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

    Neuronpedia

    INDEX
    Explanations

    page numbering and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oppression
    0.53
     ато
    0.50
     conséquences
    0.49
     جذب
    0.48
     bezpečnost
    0.47
     isotopes
    0.47
     imprisonment
    0.46
     detoxification
    0.46
     desviación
    0.45
     adsorption
    0.45
    POSITIVE LOGITS
    are
    0.50
    ak
    0.46
    ren
    0.46
    roe
    0.46
    in
    0.44
    ART
    0.43
    рто
    0.43
    er
    0.43
     sealed
    0.43
    rite
    0.42
    Act Density 0.001%

    No Known Activations