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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ла
    -0.07
    meta
    -0.06
     freelancer
    -0.06
    Objects
    -0.06
    .payload
    -0.06
    .apache
    -0.06
    '''↵
    -0.06
    ogs
    -0.06
    _Header
    -0.06
    ら
    -0.06
    POSITIVE LOGITS
     smrt
    0.07
     dejting
    0.07
     HCI
    0.07
     IKE
    0.07
    ©©
    0.07
     YÖ
    0.07
    _EST
    0.06
    _HS
    0.06
    little
    0.06
     Amnesty
    0.06
    Act Density 0.042%

    No Known Activations