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

    Neuronpedia

    INDEX
    Explanations

    shackles, control, company, listening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ри
    0.51
    ధాన
    0.50
     Organización
    0.49
    大陸
    0.48
     pomiędzy
    0.48
     journée
    0.48
     између
    0.47
    违反
    0.47
     tierra
    0.47
     Stan
    0.47
    POSITIVE LOGITS
    os
    0.62
    in
    0.59
    er
    0.54
    inho
    0.48
    ৩৮
    0.46
    otr
    0.46
    ated
    0.46
    ator
    0.45
    ers
    0.45
     br
    0.45
    Act Density 0.001%

    No Known Activations