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

    Neuronpedia

    INDEX
    Explanations

    job

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jap
    -0.07
     SHOULD
    -0.06
     Pur
    -0.06
     badges
    -0.06
     traveler
    -0.06
     dialogue
    -0.06
     missions
    -0.06
     troubled
    -0.06
    relevant
    -0.06
     architectural
    -0.06
    POSITIVE LOGITS
    _Msp
    0.07
     illuminated
    0.07
     vrch
    0.07
    Unavailable
    0.07
    \L
    0.06
    竟
    0.06
     非
    0.06
    silent
    0.06
    	EXPECT
    0.06
    ічні
    0.06
    Act Density 0.011%

    No Known Activations