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

    Neuronpedia

    INDEX
    Explanations

    audio video processing editing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вейца
    0.79
    <start_of_turn>
    0.72
    verhalten
    0.70
     mathematic
    0.68
    <unused39>
    0.68
    etze
    0.66
     Verhalten
    0.66
     파인더
    0.66
    <unused75>
    0.64
     exhaustive
    0.62
    POSITIVE LOGITS
     clips
    1.25
     clip
    1.22
     transcription
    1.20
    Transcription
    1.16
     Transcription
    1.16
     transcript
    1.15
     editing
    1.14
     conferencing
    1.12
     recording
    1.08
     Editing
    1.05
    Act Density 0.298%

    No Known Activations