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

    Neuronpedia

    INDEX
    Explanations

    objects becoming something else

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ते
    0.41
     concern
    0.39
    觥
    0.38
    rophes
    0.38
    arti
    0.37
    ర్థి
    0.37
    ells
    0.37
    ibold
    0.37
    𒋗
    0.37
     hace
    0.37
    POSITIVE LOGITS
    Clone
    0.46
     cloning
    0.45
     lup
    0.44
     lod
    0.44
     Clone
    0.43
     cloned
    0.43
     eyes
    0.42
     Lup
    0.42
     mystery
    0.41
     кло
    0.41
    Act Density 0.000%

    No Known Activations