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

    Neuronpedia

    INDEX
    Explanations

    interpret

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shop
    -0.07
     conect
    -0.06
    575
    -0.06
    ONO
    -0.06
    +z
    -0.06
    �
    -0.06
    _on
    -0.06
     collision
    -0.06
     campaigners
    -0.06
     sandwiches
    -0.06
    POSITIVE LOGITS
     interpret
    0.14
     Interpret
    0.13
     interpretation
    0.13
     interpreting
    0.12
     interpre
    0.11
     interpreted
    0.11
     interpretations
    0.11
    interpreted
    0.10
    interpre
    0.10
    Interpreter
    0.09
    Act Density 0.013%

    No Known Activations