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

    Neuronpedia

    INDEX
    Explanations

    potent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    achel
    -0.09
     Membership
    -0.07
    OfBirth
    -0.07
     Cruise
    -0.07
    _AMOUNT
    -0.07
    .Progress
    -0.07
    timeline
    -0.07
     désormais
    -0.07
     hires
    -0.07
    팹
    -0.07
    POSITIVE LOGITS
    _wind
    0.08
     enhance
    0.07
    ご利用
    0.07
    get
    0.06
    _COD
    0.06
    _filename
    0.06
     had
    0.06
    (Edit
    0.06
     platform
    0.06
     Attention
    0.06
    Act Density 0.006%

    No Known Activations