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

    Neuronpedia

    INDEX
    Explanations

    snippet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    los
    -0.08
     оз
    -0.07
    tim
    -0.07
    angi
    -0.07
    Raised
    -0.07
    .AppCompatActivity
    -0.07
    health
    -0.06
    	Field
    -0.06
     THR
    -0.06
    .AC
    -0.06
    POSITIVE LOGITS
     Particularly
    0.07
     snippet
    0.07
     Pretty
    0.06
     sensible
    0.06
     cookie
    0.06
     Kem
    0.06
    rimp
    0.06
    Snippet
    0.06
     सकत
    0.06
    unning
    0.06
    Act Density 0.002%

    No Known Activations