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

    Neuronpedia

    INDEX
    Explanations

    three.js code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reliability
    -0.08
    CERT
    -0.07
     from
    -0.07
    when
    -0.07
    Cor
    -0.07
    aism
    -0.07
    individual
    -0.07
    Prescription
    -0.07
    CEC
    -0.07
    Nth
    -0.07
    POSITIVE LOGITS
    _setup
    0.11
     setup
    0.11
    	setup
    0.11
     eingerichtet
    0.10
     stwor
    0.10
     Setup
    0.10
    .setup
    0.10
     amén
    0.09
     камеры
    0.09
     setups
    0.09
    Act Density 0.003%

    No Known Activations