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

    Neuronpedia

    INDEX
    Explanations

    volumes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DCF
    -0.07
    .pyplot
    -0.06
    _weights
    -0.06
    VERRIDE
    -0.06
    (Register
    -0.06
    ENC
    -0.06
     Replica
    -0.06
     serene
    -0.06
    jection
    -0.06
    .com
    -0.06
    POSITIVE LOGITS
     Sự
    0.07
    _claim
    0.07
     dysfunctional
    0.07
    thank
    0.07
    icare
    0.07
     dated
    0.06
     circa
    0.06
     expressing
    0.06
    .sections
    0.06
    (Long
    0.06
    Act Density 0.041%

    No Known Activations