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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imageView
    -0.07
     predic
    -0.06
    _predict
    -0.06
     cường
    -0.06
    .depth
    -0.06
    ัค
    -0.06
    uman
    -0.06
    熊
    -0.06
    -aligned
    -0.06
     propensity
    -0.06
    POSITIVE LOGITS
     likewise
    0.06
    userData
    0.06
    everyone
    0.06
     any
    0.06
    ;↵↵↵
    0.06
     meydana
    0.06
     nightmares
    0.06
     ustanov
    0.06
    ीआई
    0.06
     trash
    0.06
    Act Density 0.005%

    No Known Activations