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

    Neuronpedia

    INDEX
    Explanations

    direct recommendation or probability analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ai
    0.48
    thole
    0.46
    es
    0.46
    elow
    0.46
    eters
    0.45
    ang
    0.43
    el
    0.43
    ll
    0.43
     Loss
    0.42
    ge
    0.42
    POSITIVE LOGITS
    峹
    0.50
     exhort
    0.48
     توصیه
    0.47
    𝟘
    0.46
     kapsam
    0.46
    ⟋
    0.46
     attenuated
    0.46
     데이터를
    0.45
     innych
    0.45
    建設
    0.44
    Act Density 0.000%

    No Known Activations