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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Reserved
    -0.07
    meno
    -0.06
    onesia
    -0.06
    grand
    -0.06
    dba
    -0.06
     composing
    -0.06
    	println
    -0.06
     Fra
    -0.06
    	assertThat
    -0.06
    .reserve
    -0.06
    POSITIVE LOGITS
    RESH
    0.09
    elho
    0.07
    Tax
    0.07
     collapses
    0.07
     lifted
    0.06
     MSR
    0.06
     alo
    0.06
     lil
    0.06
     lip
    0.06
    범
    0.06
    Act Density 0.017%

    No Known Activations