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

    Neuronpedia

    INDEX
    Explanations

    stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inc
    -0.28
    orus
    -0.27
     planning
    -0.27
    è§ĦåĪĴ
    -0.25
    enc
    -0.25
    以èī²
    -0.25
    yclic
    -0.25
     colore
    -0.24
     Site
    -0.24
     Phil
    -0.24
    POSITIVE LOGITS
    bat
    0.26
     proprietor
    0.25
    æĬķ
    0.25
    gua
    0.25
    让大家
    0.24
    sets
    0.24
     hu
    0.24
    ispens
    0.24
    æĬ¼éĩij
    0.24
     rescued
    0.24
    Act Density 0.007%

    No Known Activations