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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alternative
    -0.07
    Entries
    -0.06
    艮
    -0.06
    cff
    -0.06
    楚
    -0.06
    末
    -0.06
     Cross
    -0.06
    態度
    -0.06
     Charlotte
    -0.06
    ye
    -0.06
    POSITIVE LOGITS
     erot
    0.07
    \
↵
    0.07
    (Media
    0.07
    _SYN
    0.07
    orWhere
    0.07
    _OT
    0.07
     לעית
    0.07
     Между
    0.06
    Robert
    0.06
     עסק
    0.06
    Act Density 0.024%

    No Known Activations