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

    Neuronpedia

    INDEX
    Explanations

    difference, shift

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yı
    -0.07
    řejmě
    -0.07
     ldap
    -0.06
    pton
    -0.06
     Pier
    -0.06
     포
    -0.06
    ��
    -0.06
    olin
    -0.06
     LAP
    -0.06
    orary
    -0.06
    POSITIVE LOGITS
     função
    0.07
     slick
    0.07
     intestinal
    0.06
    ReturnType
    0.06
     Ranked
    0.06
    .validation
    0.06
    Update
    0.06
    tura
    0.06
     факти
    0.06
    CLUDING
    0.06
    Act Density 0.007%

    No Known Activations