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

    Neuronpedia

    INDEX
    Explanations

    Code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Header
    -0.07
    .textAlignment
    -0.06
    ’nda
    -0.06
    XD
    -0.06
     مدل
    -0.06
    ová
    -0.06
     tob
    -0.06
    ших
    -0.06
     Lehr
    -0.06
    لو
    -0.06
    POSITIVE LOGITS
     прек
    0.08
     business
    0.07
     promptly
    0.06
     dismay
    0.06
     less
    0.06
     spreads
    0.06
     nag
    0.06
    .instant
    0.06
     stretched
    0.06
    	cp
    0.06
    Act Density 0.002%

    No Known Activations