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

    Neuronpedia

    INDEX
    Explanations

    iu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _objects
    -0.07
    ernaut
    -0.07
     subj
    -0.06
     benim
    -0.06
     Ped
    -0.06
    ็บ
    -0.06
     άλ
    -0.06
     bour
    -0.06
    亡
    -0.06
     الف
    -0.06
    POSITIVE LOGITS
     Gupta
    0.07
     strftime
    0.07
    tweets
    0.06
     LGBTQ
    0.06
    Frank
    0.06
    에는
    0.06
     False
    0.06
     …
    0.06
    Generate
    0.06
     Generate
    0.06
    Act Density 0.000%

    No Known Activations