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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adele
    -0.07
    기를
    -0.07
    gui
    -0.07
    ších
    -0.07
     almış
    -0.06
    으나
    -0.06
     �
    -0.06
     shield
    -0.06
     Our
    -0.06
     smoothing
    -0.06
    POSITIVE LOGITS
    _jump
    0.07
    _reply
    0.06
     overseas
    0.06
    ////////////////////////////////////////////////////////////////////////////////↵
    0.06
    ************
    0.06
    usted
    0.06
    TRUE
    0.06
     тех
    0.06
    reply
    0.06
     PROVID
    0.06
    Act Density 0.002%

    No Known Activations