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

    Neuronpedia

    INDEX
    Explanations

    specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ch
    -0.07
     Thick
    -0.07
    lers
    -0.07
     hateful
    -0.06
    yard
    -0.06
    Chr
    -0.06
     LIN
    -0.06
    �
    -0.06
    餐
    -0.06
    "P
    -0.06
    POSITIVE LOGITS
     maior
    0.06
    GRAPH
    0.06
     ostream
    0.06
     slapped
    0.06
     talent
    0.06
     rust
    0.06
    -around
    0.06
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    0.06
    �
    0.06
     overwhelmingly
    0.06
    Act Density 0.023%

    No Known Activations