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

    Neuronpedia

    INDEX
    Explanations

    section 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }}:=\
    0.40
     阅读全文
    0.39
    ություններ
    0.39
     etcétera
    0.39
     කියලා
    0.37
    ...!
    0.36
    <unused99>
    0.35
    abhavo
    0.35
    宽高
    0.34
    从而
    0.34
    POSITIVE LOGITS
     Performance
    0.53
     Establishing
    0.52
     Similar
    0.48
     Suggest
    0.47
     Early
    0.47
     Partial
    0.47
     Potential
    0.47
     Lead
    0.47
     Targeted
    0.46
     Ongoing
    0.46
    Act Density 2.503%

    No Known Activations