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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    уру
    -0.06
    -send
    -0.06
     consensus
    -0.06
     gadgets
    -0.06
    ังกล
    -0.06
     Awareness
    -0.06
     Hospitals
    -0.06
     Mom
    -0.06
    lfw
    -0.06
     Specify
    -0.06
    POSITIVE LOGITS
    Establish
    0.07
    adx
    0.07
    rom
    0.07
    ROM
    0.07
    .hstack
    0.06
    Ste
    0.06
    .week
    0.06
    BUILD
    0.06
     держ
    0.06
    )new
    0.06
    Act Density 0.109%

    No Known Activations