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

    Neuronpedia

    INDEX
    Explanations

    yards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     çevre
    -0.08
    esture
    -0.06
    Manufact
    -0.06
     마
    -0.06
    _topology
    -0.06
    chemistry
    -0.06
     Jugend
    -0.06
     міс
    -0.06
    	Ext
    -0.06
     confess
    -0.06
    POSITIVE LOGITS
     cir
    0.07
    thumbs
    0.06
    -taking
    0.06
     nimi
    0.06
     HUGE
    0.06
    affles
    0.06
     نی
    0.06
     mute
    0.06
     Чи
    0.06
     Iraqi
    0.06
    Act Density 0.017%

    No Known Activations