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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (mappedBy
    -0.07
    Follow
    -0.07
    ु
    -0.07
    -$
    -0.07
     Григор
    -0.06
     与
    -0.06
     edilm
    -0.06
     Forms
    -0.06
    -present
    -0.06
    ुड
    -0.06
    POSITIVE LOGITS
     Uno
    0.06
     그녀는
    0.06
    ugging
    0.06
    uliar
    0.06
    Indexes
    0.06
     niece
    0.06
    ,node
    0.06
     mocker
    0.06
     Acrobat
    0.06
     fauc
    0.06
    Act Density 0.055%

    No Known Activations