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

    Neuronpedia

    INDEX
    Explanations

    RIS-V ISA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    marshalN
    0.36
    શન
    0.35
     craindre
    0.35
    唥
    0.35
    zynarod
    0.35
    են
    0.35
    ahooks
    0.34
    പ്പെടുന്നു
    0.34
    鳧
    0.34
     dhinak
    0.34
    POSITIVE LOGITS
    the
    0.36
    <em>
    0.32
     the
    0.31
    The
    0.31
    ↵↵
    0.30
     control
    0.30
    Code
    0.30
     regulate
    0.30
    的
    0.30
     for
    0.29
    Act Density 0.203%

    No Known Activations