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
     consultations
    -0.08
     pilgrims
    -0.07
     fortalecer
    -0.07
    ILD
    -0.07
     sosten
    -0.07
     strengthening
    -0.07
     사례
    -0.07
     GOLD
    -0.07
     hre
    -0.07
    _locked
    -0.06
    POSITIVE LOGITS
     concise
    0.12
     terse
    0.12
     minimalist
    0.12
     brev
    0.11
     succinct
    0.10
     Minimal
    0.10
     компакт
    0.10
    Minimal
    0.09
    brevi
    0.09
     minimized
    0.09
    Act Density 0.015%

    No Known Activations