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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FOR
    -0.08
    xc
    -0.07
    "))↵
    -0.07
    82
    -0.07
    ']);↵
    -0.07
     for
    -0.07
     noir
    -0.07
    ")),
    -0.07
     fasta
    -0.07
    "]))↵
    -0.06
    POSITIVE LOGITS
    _APPRO
    0.07
     Approved
    0.07
    альному
    0.07
     메
    0.06
    мент
    0.06
     UserProfile
    0.06
     Rudy
    0.06
    帖
    0.06
     безпеки
    0.06
    _Details
    0.06
    Act Density 0.010%

    No Known Activations