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

    Neuronpedia

    INDEX
    Explanations

    vector

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Joyce
    -0.07
     Cra
    -0.07
     madness
    -0.07
     casino
    -0.07
     Mari
    -0.06
    dojo
    -0.06
    .isNotEmpty
    -0.06
     Neh
    -0.06
     SHR
    -0.06
    ynn
    -0.06
    POSITIVE LOGITS
    Vector
    0.09
     vector
    0.09
    に向
    0.08
     vectors
    0.08
    vec
    0.07
    Vec
    0.07
     Vector
    0.07
    320
    0.07
    оф
    0.07
     각
    0.07
    Act Density 0.018%

    No Known Activations