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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chu
    -0.07
     zun
    -0.07
    .iso
    -0.06
     interacting
    -0.06
     увелич
    -0.06
     ().
    -0.06
    //"
    -0.06
     advocates
    -0.06
     potentials
    -0.06
     mattress
    -0.06
    POSITIVE LOGITS
     सद
    0.07
    .setAlignment
    0.07
     NotFound
    0.07
     PTSD
    0.06
    aload
    0.06
     overloaded
    0.06
    (None
    0.06
     outweigh
    0.06
    流量
    0.06
     appoint
    0.06
    Act Density 0.007%

    No Known Activations