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
    Ч
    -0.07
     recognition
    -0.06
     teased
    -0.06
     balance
    -0.06
    Sampler
    -0.06
     complicated
    -0.06
     Isa
    -0.06
    aphore
    -0.06
     follows
    -0.06
    father
    -0.06
    POSITIVE LOGITS
    .Mod
    0.07
     гру
    0.06
     dane
    0.06
    +z
    0.06
     kil
    0.06
    ……。
    0.06
     vom
    0.06
     grues
    0.06
    /****************************************************************************↵
    0.06
     "),↵
    0.06
    Act Density 0.034%

    No Known Activations