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

    Neuronpedia

    INDEX
    Explanations

    Who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    man
    -0.08
     language
    -0.07
    ल
    -0.07
    ли
    -0.07
    ব
    -0.07
    റ
    -0.07
     Commonwealth
    -0.07
    ܢ
    -0.07
    },
↵
↵
    -0.07
     loophole
    -0.07
    POSITIVE LOGITS
    抢占
    0.08
    _member
    0.08
     presently
    0.07
     OH
    0.07
     MQTT
    0.07
    _gift
    0.06
     removeAll
    0.06
    .GetKey
    0.06
     �
    0.06
     conced
    0.06
    Act Density 0.338%

    No Known Activations