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

    Neuronpedia

    INDEX
    Explanations

    MP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лоб
    -0.07
     перв
    -0.06
    Microsoft
    -0.06
    θη
    -0.06
     плот
    -0.06
     нич
    -0.06
    _IDLE
    -0.06
     vez
    -0.06
    ριο
    -0.06
    шив
    -0.06
    POSITIVE LOGITS
    realloc
    0.07
     Collaboration
    0.06
     стать
    0.06
     melodies
    0.06
    .decoder
    0.06
     борь
    0.06
    	inter
    0.06
    .visual
    0.06
     研
    0.06
    .view
    0.06
    Act Density 0.090%

    No Known Activations