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

    Neuronpedia

    INDEX
    Explanations

    growing dread

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ദ്ര
    0.42
     resultMap
    0.40
    грама
    0.40
     млн
    0.39
     అవకాశ
    0.38
     lipoprotein
    0.38
    纭
    0.38
     Proteins
    0.38
    一脸
    0.37
    วรร
    0.37
    POSITIVE LOGITS
    Sel
    0.40
    Mead
    0.37
    Ί
    0.37
    abol
    0.36
     Compiled
    0.36
    釵
    0.36
     slip
    0.35
     vei
    0.35
     pasada
    0.35
     Guid
    0.35
    Act Density 0.002%

    No Known Activations