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

    Neuronpedia

    INDEX
    Explanations

    single digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     excav
    -0.06
    >C
    -0.06
     Shed
    -0.06
     trav
    -0.06
     moh
    -0.06
     performs
    -0.06
     rem
    -0.06
     fraction
    -0.06
     substantially
    -0.06
     virtually
    -0.06
    POSITIVE LOGITS
     europ
    0.07
    .hits
    0.06
    باش
    0.06
    tweets
    0.06
    �
    0.06
    िकत
    0.06
    	mov
    0.06
    番組
    0.06
    ीफ
    0.06
    айте
    0.06
    Act Density 0.004%

    No Known Activations