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

    Neuronpedia

    INDEX
    Explanations

    numbers and measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cgi
    -0.06
     fb
    -0.06
    Dub
    -0.06
     bam
    -0.06
    visions
    -0.06
     send
    -0.06
     congratulate
    -0.06
     libros
    -0.06
    ("/")↵
    -0.06
     rub
    -0.06
    POSITIVE LOGITS
     discriminatory
    0.07
    リー
    0.06
    SN
    0.06
     세계
    0.06
    _execute
    0.06
    _added
    0.06
     ResultSet
    0.06
    opro
    0.06
     filles
    0.06
     genesis
    0.06
    Act Density 0.292%

    No Known Activations