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

    Neuronpedia

    INDEX
    Explanations

    Numbers and calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    根据
    -0.08
     escalate
    -0.07
     expansión
    -0.07
    ि�
    -0.07
     escal
    -0.07
    ിയ
    -0.07
    ിയായ
    -0.07
    都
    -0.07
    itäts
    -0.07
     Institutional
    -0.07
    POSITIVE LOGITS
     decrement
    0.13
     తగ్గ
    0.12
     vermind
    0.11
     diminution
    0.10
     diminu
    0.10
     ઘટાડ
    0.10
     감소
    0.10
    减少
    0.10
     zmanjš
    0.10
     disminuir
    0.10
    Act Density 0.074%

    No Known Activations