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

    Neuronpedia

    INDEX
    Explanations

    announcements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igators
    -0.07
    Search
    -0.06
     CVS
    -0.06
     contagious
    -0.06
    _SOFT
    -0.06
     순
    -0.06
     distorted
    -0.06
     deux
    -0.06
    sports
    -0.06
     단
    -0.06
    POSITIVE LOGITS
    /accounts
    0.08
     tease
    0.07
    Brains
    0.07
    ismet
    0.07
    (exc
    0.06
     lawmakers
    0.06
     Delete
    0.06
     yeme
    0.06
    esson
    0.06
    ahir
    0.06
    Act Density 0.059%

    No Known Activations