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

    Neuronpedia

    INDEX
    Explanations

    Java code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    auss
    -0.06
    coni
    -0.06
    _ans
    -0.06
    ahrenheit
    -0.06
    .magic
    -0.06
    ileen
    -0.06
    	ok
    -0.06
    ienia
    -0.06
    333
    -0.06
     ji
    -0.06
    POSITIVE LOGITS
     configuring
    0.07
     glimps
    0.06
    (md
    0.06
     jog
    0.06
    KeyValue
    0.06
     extracting
    0.06
     komp
    0.06
     descend
    0.06
    ulnerable
    0.06
     clickable
    0.06
    Act Density 0.001%

    No Known Activations