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

    Neuronpedia

    INDEX
    Explanations

    ag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    accion
    -0.07
     Pref
    -0.07
    ICC
    -0.07
     indu
    -0.07
    델
    -0.07
     readers
    -0.07
    Rec
    -0.07
     sparing
    -0.06
     Plane
    -0.06
    _kv
    -0.06
    POSITIVE LOGITS
        
↵
    0.07
    opard
    0.06
     tão
    0.06
     hus
    0.06
     expr
    0.06
     initialise
    0.06
    "),
↵
    0.06
     astounding
    0.06
    Philadelphia
    0.06
     optimizations
    0.06
    Act Density 0.001%

    No Known Activations