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

    Neuronpedia

    INDEX
    Explanations

    exclusive access, offers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Defines
    -0.07
    .Ultra
    -0.07
    ��
    -0.07
    '#
    -0.06
    ;margin
    -0.06
     Nigeria
    -0.06
     Mỹ
    -0.06
    대로
    -0.06
     pam
    -0.06
    %
    -0.06
    POSITIVE LOGITS
    <<<<
    0.07
    �
    0.07
    .ToDouble
    0.07
    jas
    0.06
    pal
    0.06
    düğ
    0.06
    phas
    0.06
     schle
    0.06
     Fortress
    0.06
     درس
    0.06
    Act Density 0.051%

    No Known Activations