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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CREASE
    -0.07
    ogen
    -0.07
     Levine
    -0.06
     слаб
    -0.06
    Improved
    -0.06
     latest
    -0.06
    Night
    -0.06
    ellen
    -0.06
    oru
    -0.06
    .every
    -0.06
    POSITIVE LOGITS
    struction
    0.07
    ("").
    0.07
    _BORDER
    0.07
    /g
    0.06
    肩
    0.06
     mesure
    0.06
    ;br
    0.06
    builders
    0.06
     р
    0.06
     สามารถ
    0.06
    Act Density 0.035%

    No Known Activations