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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >p
    -0.06
    .members
    -0.06
    cargo
    -0.06
     failures
    -0.06
    .fft
    -0.06
    isoner
    -0.06
    Detection
    -0.06
    elt
    -0.06
    리를
    -0.06
    (progress
    -0.06
    POSITIVE LOGITS
    영
    0.07
     materi
    0.07
    green
    0.07
     JD
    0.06
    Α
    0.06
     Vox
    0.06
    ={()
    0.06
     futures
    0.06
     IPs
    0.06
    _TREE
    0.06
    Act Density 0.005%

    No Known Activations