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

    Neuronpedia

    INDEX
    Explanations

    among

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Ext
    -0.07
    onor
    -0.07
    apter
    -0.07
    Mb
    -0.07
     ओर
    -0.06
     NST
    -0.06
    oleč
    -0.06
    ract
    -0.06
    NTSTATUS
    -0.06
     wur
    -0.06
    POSITIVE LOGITS
    anges
    0.07
     attending
    0.07
     satisfy
    0.07
    ıyla
    0.06
     nostalg
    0.06
    ��
    0.06
     pesticide
    0.06
    release
    0.06
     reconstructed
    0.06
    βε
    0.06
    Act Density 0.000%

    No Known Activations