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

    Neuronpedia

    INDEX
    Explanations

    medical information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WW
    -0.07
     center
    -0.07
    Machine
    -0.06
     Score
    -0.06
     정치
    -0.06
     Everybody
    -0.06
    563
    -0.06
     "\↵
    -0.06
    .database
    -0.06
     hypothesis
    -0.06
    POSITIVE LOGITS
    _SSL
    0.07
     initializing
    0.06
    lanır
    0.06
    opp
    0.06
    ήν
    0.06
    MouseListener
    0.06
    cue
    0.06
    gard
    0.06
    comb
    0.05
     vibes
    0.05
    Act Density 0.014%

    No Known Activations