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

    Neuronpedia

    INDEX
    Explanations

    ated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .heading
    -0.07
    療
    -0.07
    Foo
    -0.07
     backers
    -0.06
     Mime
    -0.06
    _FROM
    -0.06
     sharks
    -0.06
    \u
    -0.06
     Morse
    -0.06
     deficiencies
    -0.06
    POSITIVE LOGITS
    .Ar
    0.07
    \Modules
    0.07
     德
    0.06
     lastIndex
    0.06
     escalate
    0.06
    ,opt
    0.06
     fakat
    0.06
     inlet
    0.06
    (goal
    0.06
     hourly
    0.06
    Act Density 0.001%

    No Known Activations