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

    Neuronpedia

    INDEX
    Explanations

    might

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _have
    -0.07
    청
    -0.07
    "net
    -0.07
     سعود
    -0.06
    Initializing
    -0.06
     gay
    -0.06
     Hav
    -0.06
    光
    -0.06
     Consumer
    -0.06
    "We
    -0.06
    POSITIVE LOGITS
    opor
    0.07
    grades
    0.06
    packing
    0.06
     opportun
    0.06
    :
    0.06
    _IDX
    0.06
     dishonest
    0.06
    IMATION
    0.06
     dri
    0.06
     imgs
    0.06
    Act Density 0.000%

    No Known Activations