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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    魔
    -0.07
     withd
    -0.07
    ','',
    -0.06
     '-',
    -0.06
     alerted
    -0.06
    iversit
    -0.06
     През
    -0.06
    ?"↵↵
    -0.06
    _INITIALIZER
    -0.06
     Walls
    -0.06
    POSITIVE LOGITS
     punishment
    0.07
     Laptop
    0.07
    (hash
    0.06
    idepress
    0.06
     arası
    0.06
                    
    0.06
     barbar
    0.06
    (web
    0.06
     bluetooth
    0.06
    .web
    0.06
    Act Density 0.023%

    No Known Activations