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

    Neuronpedia

    INDEX
    Explanations

    warmth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wayne
    -0.07
    -standing
    -0.07
    епти
    -0.07
    idence
    -0.07
    ็ค
    -0.06
     qualities
    -0.06
     incidence
    -0.06
    писание
    -0.06
     cheering
    -0.06
    рован
    -0.06
    POSITIVE LOGITS
     ETH
    0.07
    ,it
    0.06
     Band
    0.06
    (IB
    0.06
    -break
    0.06
    caffold
    0.06
     Negot
    0.06
    ."
    0.06
     longer
    0.06
    	delete
    0.06
    Act Density 0.022%

    No Known Activations