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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Equivalent
    -0.07
    pars
    -0.07
    APH
    -0.06
    requete
    -0.06
     skies
    -0.06
    _ly
    -0.06
     hi
    -0.06
     Hist
    -0.06
    594
    -0.06
    Sym
    -0.06
    POSITIVE LOGITS
    言った
    0.07
    \v
    0.06
    テル
    0.06
     unser
    0.06
    auté
    0.06
    =self
    0.06
    nonce
    0.06
    lude
    0.06
    После
    0.06
     istediğiniz
    0.06
    Act Density 0.024%

    No Known Activations