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

    Neuronpedia

    INDEX
    Explanations

    AI safety guidelines and prohibitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     compan
    0.46
     mathematicians
    0.44
     programmers
    0.42
     टीम
    0.41
     astronomers
    0.40
     corporations
    0.39
     team
    0.39
     scientists
    0.39
     ocur
    0.39
     engineers
    0.38
    POSITIVE LOGITS
     BASED
    0.53
    遵循
    0.51
    reinforced
    0.50
     பின்பற்ற
    0.49
     பின்ப
    0.46
     cited
    0.46
     Derived
    0.46
     reinforced
    0.46
    must
    0.45
    כת
    0.44
    Act Density 0.004%

    No Known Activations