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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    grades
    -0.07
     Πρό
    -0.07
    ToShow
    -0.07
    auge
    -0.07
    TEMP
    -0.07
     Clifford
    -0.06
    ух
    -0.06
     Ευ
    -0.06
     Німеч
    -0.06
    .DrawLine
    -0.06
    POSITIVE LOGITS
     alg
    0.07
     nod
    0.06
     homosexuals
    0.06
     jwt
    0.06
     quar
    0.06
     sil
    0.06
     fancy
    0.06
     ain
    0.06
     dynamic
    0.06
     obedient
    0.06
    Act Density 0.011%

    No Known Activations