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

    Neuronpedia

    INDEX
    Explanations

    price features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tumultuous
    0.50
     cumulative
    0.46
     tension
    0.46
     severe
    0.45
     wasteful
    0.45
     contemplative
    0.45
     expiration
    0.42
    टीसी
    0.41
     trauma
    0.41
     a
    0.41
    POSITIVE LOGITS
    мма
    0.51
    IRA
    0.43
    Р
    0.42
    蠡
    0.41
     lingk
    0.41
    唂
    0.41
    Ра
    0.40
    на
    0.40
     lika
    0.39
     roupas
    0.39
    Act Density 0.003%

    No Known Activations