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

    Neuronpedia

    INDEX
    Explanations

    on behalf of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parameterType
    0.80
    Sight
    0.76
    bounds
    0.76
     eP
    0.75
     sight
    0.73
     uống
    0.72
     flashbacks
    0.71
     (($
    0.71
     incidence
    0.70
    gia
    0.70
    POSITIVE LOGITS
    হ
    0.89
    আ
    0.81
     behalf
    0.80
    žne
    0.77
    𝗇
    0.74
     prije
    0.73
    immersive
    0.71
     pedibusque
    0.70
     त्यावेळी
    0.70
    ە
    0.67
    Act Density 0.067%

    No Known Activations