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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     огром
    -0.08
     graves
    -0.07
    فاده
    -0.07
    очных
    -0.07
     youthful
    -0.07
     ταιν
    -0.07
     continuar
    -0.07
    زية
    -0.07
    .Mobile
    -0.07
    icích
    -0.06
    POSITIVE LOGITS
     dest
    0.06
     composing
    0.06
     Kin
    0.06
     autoc
    0.06
    	D
    0.06
     created
    0.06
    umbled
    0.05
    mm
    0.05
    i
    0.05
     kork
    0.05
    Act Density 0.001%

    No Known Activations