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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     редак
    -0.08
    ర్జ
    -0.07
     которого
    -0.07
     Engine
    -0.07
    ર્જ
    -0.07
     BIS
    -0.07
     Э
    -0.07
    ,the
    -0.07
    �
    -0.07
    ikku
    -0.07
    POSITIVE LOGITS
    /etc
    0.09
    その他
    0.08
     disrupting
    0.08
     disrupt
    0.08
    igit
    0.08
    liess
    0.07
     disf
    0.07
    0.07
     आव
    0.07
     disrupted
    0.07
    Act Density 0.210%
    No Known Activations