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

    Neuronpedia

    INDEX
    Explanations

    talking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ownership
    -0.06
    zk
    -0.06
     renewables
    -0.06
     standards
    -0.06
     Vš
    -0.06
    .Progress
    -0.06
     Execution
    -0.06
    precision
    -0.06
     vet
    -0.06
    ันด
    -0.05
    POSITIVE LOGITS
    -lib
    0.07
     ust
    0.07
     बर
    0.07
     голова
    0.07
    ongan
    0.07
     (__
    0.06
    ?[
    0.06
    flamm
    0.06
    .px
    0.06
    uble
    0.06
    Act Density 0.032%

    No Known Activations