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

    Neuronpedia

    INDEX
    Explanations

    risk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     synaptic
    -0.08
     müzik
    -0.07
     progen
    -0.06
    427
    -0.06
     complied
    -0.06
     sequences
    -0.06
    (*)(
    -0.06
     compensated
    -0.06
    ㅇ
    -0.06
     Nearly
    -0.06
    POSITIVE LOGITS
     risking
    0.09
     khiển
    0.07
    มน
    0.07
    .YES
    0.07
     cresc
    0.07
    xit
    0.06
     Yorkshire
    0.06
    SSI
    0.06
     ritual
    0.06
     imaginable
    0.06
    Act Density 0.004%

    No Known Activations