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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Int
    -0.06
     Hate
    -0.06
     год
    -0.06
    Tracks
    -0.06
     THINK
    -0.06
     kings
    -0.06
     Repeat
    -0.06
    	sleep
    -0.06
     Todo
    -0.05
    sql
    -0.05
    POSITIVE LOGITS
     Queries
    0.07
     pla
    0.06
     hydrogen
    0.06
     hydration
    0.06
     Cookies
    0.06
     circumcision
    0.06
     backstage
    0.06
    อพ
    0.06
    UNS
    0.06
    ülen
    0.06
    Act Density 0.057%

    No Known Activations