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

    Neuronpedia

    INDEX
    Explanations

    Special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ment
    -0.07
    _proj
    -0.07
     @
    -0.06
     receptions
    -0.06
    Shop
    -0.06
    _atual
    -0.06
     против
    -0.06
    ане
    -0.06
     �
    -0.06
    242
    -0.06
    POSITIVE LOGITS
    |=↵
    0.07
     MPG
    0.07
    iators
    0.06
    .ToolStrip
    0.06
     Curt
    0.06
     Upon
    0.06
     Heidi
    0.06
    ीमत
    0.06
    _Action
    0.06
     mistaken
    0.06
    Act Density 0.016%

    No Known Activations