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

    Neuronpedia

    INDEX
    Explanations

    processing and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sub
    0.41
    каз
    0.41
     dominio
    0.41
     momento
    0.38
     коммуна
    0.37
     nég
    0.36
     matéria
    0.36
     moment
    0.35
     examined
    0.35
     pubblica
    0.35
    POSITIVE LOGITS
    Eternal
    0.50
    Philippines
    0.40
    Export
    0.40
     Posterior
    0.40
    Kentucky
    0.39
    Miss
    0.39
    Assignment
    0.39
    Industrial
    0.38
    Algorithm
    0.37
    Next
    0.37
    Act Density 0.000%

    No Known Activations