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

    Neuronpedia

    INDEX
    Explanations

    Timestamps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Place
    -0.07
    echa
    -0.07
     crosses
    -0.07
    thin
    -0.07
    add
    -0.07
    -my
    -0.06
    /embed
    -0.06
    ети
    -0.06
    assessment
    -0.06
    Digits
    -0.06
    POSITIVE LOGITS
    促
    0.07
    .wx
    0.06
    itbart
    0.06
     كام
    0.06
     Soft
    0.06
     الض
    0.06
     Phần
    0.06
    *******************************************************************************/↵
    0.05
    ослав
    0.05
    vertime
    0.05
    Act Density 0.005%

    No Known Activations