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

    Neuronpedia

    INDEX
    Explanations

    code, punctuation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     operative
    -0.07
     слух
    -0.06
    losti
    -0.06
     climbers
    -0.06
     prevalence
    -0.06
    ुड
    -0.06
    ाओ
    -0.06
    off
    -0.06
    ーブ
    -0.06
     Possible
    -0.06
    POSITIVE LOGITS
    '];
    0.07
    ="?
    0.07
     yet
    0.07
     Vall
    0.06
    иболее
    0.06
    )—
    0.06
    "'
    0.06
     Вер
    0.06
    ="<?
    0.06
     quint
    0.06
    Act Density 0.063%

    No Known Activations