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

    Neuronpedia

    INDEX
    Explanations

    wither, er

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pus
    -0.07
     Olsen
    -0.07
    (log
    -0.07
     traum
    -0.07
    log
    -0.07
    忙
    -0.07
     Dar
    -0.07
     log
    -0.07
    ways
    -0.07
    FLAG
    -0.07
    POSITIVE LOGITS
     Infantry
    0.08
    -faced
    0.08
     portraits
    0.08
     sede
    0.07
    Gil
    0.07
     தலைம
    0.07
    �
    0.07
     Atlantic
    0.07
     Grip
    0.07
     cruc
    0.07
    Act Density 0.003%

    No Known Activations