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

    Neuronpedia

    INDEX
    Explanations

    urban canyon Effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     microbiology
    0.52
     correspondents
    0.50
     metadata
    0.49
     dyslex
    0.48
     prompts
    0.46
     specificity
    0.45
     germination
    0.45
    genres
    0.45
     metaphysics
    0.45
     microphones
    0.45
    POSITIVE LOGITS
    비를
    0.57
    OutputDir
    0.54
    agge
    0.51
     രംഗ
    0.49
     equipe
    0.47
    initpos
    0.46
    addListener
    0.46
     группе
    0.46
     அல்லது
    0.45
    лить
    0.45
    Act Density 0.001%

    No Known Activations