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

    Neuronpedia

    INDEX
    Explanations

    Hey everyone, welcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     살펴보도록
    0.60
     entrevist
    0.54
     साक्षात्कार
    0.51
     entsprechend
    0.49
     introduit
    0.49
     interviewee
    0.48
     entrevista
    0.48
     olacaktır
    0.48
     entrevistas
    0.48
     Interview
    0.47
    POSITIVE LOGITS
    com
    0.52
    Lock
    0.47
    That
    0.46
    lock
    0.44
    plus
    0.44
    Like
    0.44
    ص
    0.44
    Warning
    0.42
    Federal
    0.42
    Whether
    0.42
    Act Density 0.001%

    No Known Activations