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

    Neuronpedia

    INDEX
    Explanations

    vec

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slain
    -0.08
    .lower
    -0.08
    326
    -0.07
     Milton
    -0.07
     Marilyn
    -0.07
     ACTION
    -0.07
     Barton
    -0.06
     Arsenal
    -0.06
     أل
    -0.06
    "N
    -0.06
    POSITIVE LOGITS
     पह
    0.07
     никогда
    0.07
    AT
    0.07
    _buf
    0.07
    _interp
    0.07
     Tracker
    0.07
    .paging
    0.07
    (Vec
    0.07
    �
    0.06
     голова
    0.06
    Act Density 0.005%

    No Known Activations