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
    .findById
    -0.07
     통해
    -0.07
    していた
    -0.06
     forcefully
    -0.06
    中
    -0.06
    _hooks
    -0.06
    teachers
    -0.06
    _MOD
    -0.06
    signals
    -0.06
    Scheme
    -0.06
    POSITIVE LOGITS
     moh
    0.06
     unwind
    0.06
     maxY
    0.06
     UserProfile
    0.06
    urious
    0.06
    unc
    0.06
    !';↵
    0.06
     jose
    0.06
     Wildlife
    0.06
    puted
    0.06
    Act Density 0.000%

    No Known Activations