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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    045
    -0.07
     Signals
    -0.06
     Drops
    -0.06
    romise
    -0.06
    泳
    -0.06
    using
    -0.06
     passionate
    -0.06
    glm
    -0.06
     informant
    -0.06
    POSITIVE LOGITS
     WTF
    0.07
    eries
    0.06
     disgr
    0.06
    	Key
    0.06
     م
    0.06
    웠
    0.06
     creation
    0.06
    TX
    0.06
     Innov
    0.06
    Comput
    0.06
    Act Density 0.022%

    No Known Activations