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

    Neuronpedia

    INDEX
    Explanations

    dn

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lude
    -0.09
     condition
    -0.08
     isolate
    -0.07
     monuments
    -0.07
     colours
    -0.07
     Links
    -0.07
    uct
    -0.07
     To
    -0.07
    nde
    -0.07
    _c
    -0.07
    POSITIVE LOGITS
     improper
    0.08
    amacare
    0.07
    威名
    0.07
     decorators
    0.07
     boyc
    0.07
    _featured
    0.07
    솥
    0.07
    #!
    0.07
    ╕
    0.07
     pregn
    0.06
    Act Density 0.000%

    No Known Activations