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

    Neuronpedia

    INDEX
    Explanations

    Code/Wizard interface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Phoenix
    -0.07
    .mb
    -0.07
     Conditions
    -0.07
    _h
    -0.06
     urls
    -0.06
    _mC
    -0.06
    _cookies
    -0.06
     Kr
    -0.06
     Subject
    -0.06
    回
    -0.06
    POSITIVE LOGITS
     disadv
    0.07
    Initially
    0.06
     Bund
    0.06
    /Auth
    0.06
    spb
    0.06
    VERRIDE
    0.06
    apan
    0.06
    -Aug
    0.06
     conventional
    0.06
     cafes
    0.06
    Act Density 0.021%

    No Known Activations