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

    Neuronpedia

    INDEX
    Explanations

    errors and problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Institutional
    -0.06
     spirituality
    -0.06
    xcf
    -0.06
    бор
    -0.06
     Vir
    -0.06
    belief
    -0.06
    oubles
    -0.06
    690
    -0.06
     gó
    -0.06
     Cycling
    -0.06
    POSITIVE LOGITS
     повинна
    0.07
    /stretchr
    0.06
     выбира
    0.06
    _ASSUME
    0.06
    "]
↵
    0.06
    �
    0.06
    (Edit
    0.06
    /socket
    0.06
    メリカ
    0.06
     synth
    0.06
    Act Density 0.000%

    No Known Activations