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
    thead
    -0.07
     incons
    -0.06
     pit
    -0.06
    cos
    -0.06
     Armenian
    -0.06
    illance
    -0.06
    pars
    -0.06
     mostr
    -0.06
    /status
    -0.06
    Tp
    -0.06
    POSITIVE LOGITS
     �
    0.07
     جر
    0.06
     يق
    0.06
    editing
    0.06
    $value
    0.06
     writing
    0.06
     minimise
    0.06
    ILTER
    0.06
    447
    0.06
     Passive
    0.06
    Act Density 0.069%

    No Known Activations