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

    Neuronpedia

    INDEX
    Explanations

    hassle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .font
    -0.07
     crypt
    -0.07
     psyche
    -0.07
     gboolean
    -0.07
    گار
    -0.07
     ﾞ
    -0.06
    Sem
    -0.06
    =image
    -0.06
    	include
    -0.06
    研究所
    -0.06
    POSITIVE LOGITS
     hassle
    0.17
     hass
    0.09
     Hass
    0.09
    .ssl
    0.06
    slack
    0.06
    носи
    0.06
     war
    0.06
     дина
    0.06
     harassing
    0.06
     Bek
    0.06
    Act Density 0.004%

    No Known Activations