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

    Neuronpedia

    INDEX
    Explanations

    YAML parsing and loading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䀓
    0.48
     LoginForm
    0.42
     Wexford
    0.42
    ㅀ
    0.41
    Therates
    0.40
     диф
    0.40
     polygons
    0.40
    ఫో
    0.40
     backgroundImg
    0.40
     receivables
    0.39
    POSITIVE LOGITS
     YAML
    1.26
    YAML
    1.12
    yaml
    1.09
     yaml
    1.08
     Yam
    1.06
    Yam
    0.99
    Yaml
    0.95
    yml
    0.85
     yam
    0.76
    yam
    0.70
    Act Density 0.009%

    No Known Activations