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

    Neuronpedia

    INDEX
    Explanations

    ============

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    layer
    -0.07
    requ
    -0.06
     loaded
    -0.06
     raft
    -0.06
     aliases
    -0.06
     unzip
    -0.06
    RFC
    -0.06
    Προ
    -0.06
    utivo
    -0.06
    顺
    -0.06
    POSITIVE LOGITS
     सबस
    0.07
    äsent
    0.07
     νεφοκ
    0.07
                  
↵
    0.07
     وك
    0.06
    ADING
    0.06
     lạc
    0.06
     ülkenin
    0.06
    ="'+
    0.06
     plainly
    0.06
    Act Density 0.003%

    No Known Activations