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

    Neuronpedia

    INDEX
    Explanations

    security and risk management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Meteor
    0.40
    欅
    0.40
    alke
    0.38
    Chem
    0.38
    কলাপ
    0.38
     celebrity
    0.38
    archy
    0.38
    ExternalTaskPojo
    0.38
     കമ്പ
    0.37
    Reserv
    0.37
    POSITIVE LOGITS
     proportionately
    0.49
     proportionally
    0.46
     quattro
    0.39
     insights
    0.38
     inferences
    0.38
     hawk
    0.38
    dataPro
    0.38
     partecipanti
    0.37
    insights
    0.37
     biosynthetic
    0.36
    Act Density 0.000%

    No Known Activations