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

    Neuronpedia

    INDEX
    Explanations

    property

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Uz
    -0.07
     seven
    -0.06
    353
    -0.06
     iso
    -0.06
     suppl
    -0.06
     کنار
    -0.06
     Girl
    -0.06
     assist
    -0.06
     salads
    -0.06
    Seven
    -0.06
    POSITIVE LOGITS
    juries
    0.07
    damage
    0.07
     property
    0.07
     poop
    0.07
    <!--[
    0.07
     datum
    0.07
     ближ
    0.07
    Ref
    0.07
    platz
    0.07
    ッチ
    0.07
    Act Density 0.011%

    No Known Activations