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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    larak
    -0.07
    caling
    -0.06
    Wins
    -0.06
    amation
    -0.06
    TRACE
    -0.06
    旧
    -0.06
    alles
    -0.06
    OMETRY
    -0.06
    ›
    -0.06
    Cnt
    -0.06
    POSITIVE LOGITS
    .Management
    0.07
    ezpe
    0.06
    .Append
    0.06
     seeker
    0.06
     Watching
    0.06
     onChanged
    0.06
    .EMAIL
    0.06
     conclus
    0.06
    Places
    0.06
    formatted
    0.06
    Act Density 0.115%

    No Known Activations