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

    Neuronpedia

    INDEX
    Explanations

    video content and learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cton
    0.46
     imperme
    0.44
     ቦታ
    0.44
    that
    0.44
     mực
    0.44
     mkdir
    0.43
     holiness
    0.43
     लाकर
    0.43
     cess
    0.43
     pacemaker
    0.43
    POSITIVE LOGITS
    Je
    0.44
    Ö
    0.44
    Exploring
    0.42
    Successful
    0.42
    ぶ
    0.42
    Anagram
    0.42
    Management
    0.41
    Arc
    0.41
    Parser
    0.41
    Are
    0.41
    Act Density 0.000%

    No Known Activations