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

    Neuronpedia

    INDEX
    Explanations

    `C` followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     usability
    0.55
    nomina
    0.53
     misconduct
    0.52
     problema
    0.51
     проблеми
    0.51
     deposito
    0.50
     wholesome
    0.49
    щення
    0.49
     remediation
    0.48
    راہ
    0.48
    POSITIVE LOGITS
    h
    0.63
    ابية
    0.54
     arabe
    0.54
     Shopping
    0.53
    }\,
    0.50
    H
    0.50
     Ajouter
    0.49
     Hormone
    0.49
    ల
    0.49
    හ
    0.48
    Act Density 0.000%

    No Known Activations