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

    Neuronpedia

    INDEX
    Explanations

    list table directory labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bertson
    0.57
    Aprend
    0.55
    Wat
    0.54
    Imagen
    0.53
    Warum
    0.53
     Aprend
    0.53
    𝙩
    0.52
    vict
    0.51
    Bes
    0.51
    Mo
    0.50
    POSITIVE LOGITS
     unix
    0.50
     või
    0.49
     concise
    0.48
     secretive
    0.48
    ない
    0.47
     scent
    0.47
     fat
    0.46
     libido
    0.45
     stench
    0.45
     verifiable
    0.45
    Act Density 0.000%

    No Known Activations