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

    Neuronpedia

    INDEX
    Explanations

    (risk, tolerance)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kherson
    1.07
     Hereford
    1.00
     Konya
    0.97
     Leverkusen
    0.96
     Ansible
    0.96
     Lufthansa
    0.95
     rapeseed
    0.94
     intercultural
    0.94
     FTIR
    0.94
     Sharjah
    0.94
    POSITIVE LOGITS
    ся
    0.86
    ל
    0.80
    ли
    0.76
    ן
    0.76
    aj
    0.72
    enc
    0.71
    ق
    0.70
     be
    0.69
    ée
    0.68
    inhos
    0.68
    Act Density 0.000%

    No Known Activations