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

    Neuronpedia

    INDEX
    Explanations

    locations after prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    łam
    0.73
    óst
    0.65
    talet
    0.64
    坛
    0.62
    氨
    0.62
    本格
    0.60
    asim
    0.59
    ombic
    0.59
    ımlar
    0.58
     keş
    0.58
    POSITIVE LOGITS
     Grad
    0.88
     DN
    0.82
     Pi
    0.80
    Grad
    0.79
     Cart
    0.79
    BJ
    0.74
     Ora
    0.73
     Revol
    0.73
     Ink
    0.73
     Revolution
    0.72
    Act Density 0.002%

    No Known Activations