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

    Neuronpedia

    INDEX
    Explanations

    Conversational text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dopad
    -0.07
    OUTPUT
    -0.06
     McGu
    -0.06
     fingers
    -0.06
     cohesion
    -0.06
    _FRAME
    -0.06
    ORK
    -0.06
     finger
    -0.06
    IMAGE
    -0.06
     Gin
    -0.06
    POSITIVE LOGITS
     Authentication
    0.06
    \Carbon
    0.06
     گاه
    0.06
    ."/
    0.06
    Associated
    0.06
     �
    0.06
    環
    0.06
    [curr
    0.06
     умень
    0.06
    ";}↵
    0.06
    Act Density 0.010%

    No Known Activations