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

    Neuronpedia

    INDEX
    Explanations

    dialogue transcript

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    やって
    -0.07
     ana
    -0.07
    ؟؟
    -0.07
    xyz
    -0.06
    ۳۰
    -0.06
     dok
    -0.06
     gelir
    -0.06
    入れ
    -0.06
     practitioners
    -0.06
    _aes
    -0.06
    POSITIVE LOGITS
    Authorities
    0.07
    бе
    0.07
     medic
    0.06
     Carolina
    0.06
    .newInstance
    0.06
     depressed
    0.06
     caric
    0.06
    .MESSAGE
    0.06
     Daten
    0.06
    ."},↵
    0.06
    Act Density 0.025%

    No Known Activations