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

    Neuronpedia

    INDEX
    Explanations

    ll

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ll
    -0.97
    LL
    -0.72
    lls
    -0.72
    lled
    -0.71
    COW
    -0.61
     bezig
    -0.60
    OGND
    -0.59
     Sociales
    -0.59
    __(/*!
    -0.58
     CURIAM
    -0.57
    POSITIVE LOGITS
     be
    1.26
     have
    1.05
     make
    0.84
     get
    0.79
     continue
    0.75
     bring
    0.73
     do
    0.72
     take
    0.72
     need
    0.71
     allow
    0.71
    Act Density 0.140%

    No Known Activations