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

    Neuronpedia

    INDEX
    Explanations

    narratives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -second
    -0.07
    xFE
    -0.06
     Temp
    -0.06
    caf
    -0.06
     červ
    -0.06
    navigate
    -0.06
     orient
    -0.06
     gets
    -0.06
     помещ
    -0.06
    _numer
    -0.06
    POSITIVE LOGITS
    ')
↵
    0.08
     landed
    0.07
     posed
    0.07
     did
    0.07
     arisen
    0.07
     struggled
    0.07
     survived
    0.07
     seemed
    0.07
     forgot
    0.07
     showed
    0.07
    Act Density 0.385%

    No Known Activations