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

    Neuronpedia

    INDEX
    Explanations

    scratch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nama
    -0.06
    (currentUser
    -0.06
     landlords
    -0.06
     menj
    -0.06
    'ex
    -0.06
    enef
    -0.06
     khá
    -0.06
    aired
    -0.06
     minorities
    -0.06
     Mask
    -0.06
    POSITIVE LOGITS
    서
    0.07
    -earth
    0.06
    brain
    0.06
     amateur
    0.06
    ivol
    0.06
    uencia
    0.06
    _MAKE
    0.06
     pars
    0.06
     WOW
    0.06
     outset
    0.06
    Act Density 0.011%

    No Known Activations