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

    Neuronpedia

    INDEX
    Explanations

    roots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Brightness
    -0.09
    Roster
    -0.08
     aerosol
    -0.08
    sz
    -0.08
     કરવા
    -0.07
    үл
    -0.07
    Rating
    -0.07
     χαρακ
    -0.07
     contingency
    -0.07
    spo
    -0.07
    POSITIVE LOGITS
     फैल
    0.10
     ноги
    0.09
     깊
    0.09
     enterr
    0.08
     anch
    0.08
     mighty
    0.08
     fascinating
    0.08
     anchors
    0.08
     глуб
    0.08
     сеть
    0.08
    Act Density 0.009%

    No Known Activations