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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     omega
    -0.07
    Stroke
    -0.06
     ACL
    -0.06
    stra
    -0.06
     sauna
    -0.06
    �
    -0.06
    öße
    -0.06
     lights
    -0.06
    _space
    -0.06
     lou
    -0.06
    POSITIVE LOGITS
    deal
    0.07
    нес
    0.06
    ATTRIBUTE
    0.06
    .dead
    0.06
    newValue
    0.06
    _mul
    0.06
     GetUser
    0.06
    βολ
    0.06
    یدن
    0.06
    ()."
    0.06
    Act Density 0.010%

    No Known Activations