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

    Neuronpedia

    INDEX
    Explanations

    instant nonetheless

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nonetheless
    -0.81
     nevertheless
    -0.73
     instant
    -0.66
     Instant
    -0.65
    instant
    -0.65
     embraced
    -0.59
     embrace
    -0.57
    Instant
    -0.57
    chon
    -0.56
    swe
    -0.53
    POSITIVE LOGITS
    FontOfSize
    0.62
    gelöst
    0.60
    erunner
    0.58
    antMatchers
    0.58
    brechen
    0.57
    Autoritní
    0.56
    SBATCH
    0.54
    /**
    0.54
    leth
    0.53
    antd
    0.53
    Act Density 1.598%

    No Known Activations