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

    Neuronpedia

    INDEX
    Explanations

    Names or part of names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erialization
    -0.07
     probes
    -0.07
     chipset
    -0.07
     dress
    -0.06
    ูม
    -0.06
    _SERIAL
    -0.06
    PY
    -0.06
    наслід
    -0.06
    _jobs
    -0.06
    区
    -0.06
    POSITIVE LOGITS
     Raf
    0.07
    olean
    0.06
     tzv
    0.06
     substituted
    0.06
    只能
    0.06
    ­i
    0.06
    ात
    0.06
     Stability
    0.06
     verschill
    0.06
     SCRIPT
    0.06
    Act Density 0.043%

    No Known Activations