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

    Neuronpedia

    INDEX
    Explanations

    cause

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Evo
    -0.07
     Schön
    -0.07
     subjective
    -0.07
    ,val
    -0.07
     general
    -0.07
     dof
    -0.07
     sist
    -0.07
    ㅁ
    -0.07
    ᕙ
    -0.07
    .Of
    -0.06
    POSITIVE LOGITS
     unread
    0.07
     Earlier
    0.07
     Getting
    0.07
     mentor
    0.07
    icators
    0.06
    ercises
    0.06
    Print
    0.06
    钻研
    0.06
    (User
    0.06
    Cook
    0.06
    Act Density 0.009%

    No Known Activations