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

    Neuronpedia

    INDEX
    Explanations

    legal/code blocks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	HX
    -0.28
    uros
    -0.27
    ç«ĭ
    -0.26
    rego
    -0.25
    rott
    -0.25
    .FC
    -0.25
    <$
    -0.25
    ZE
    -0.24
    èŀºæĹĭ
    -0.24
    鼶ç¢İ
    -0.24
    POSITIVE LOGITS
    _KIND
    0.28
     PURE
    0.26
     coordinated
    0.26
    èŁĬ
    0.25
     coordination
    0.24
    éĩī
    0.24
    è§ģ解
    0.24
     hát
    0.24
    ivism
    0.24
     beyond
    0.24
    Act Density 0.019%

    No Known Activations