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

    Neuronpedia

    INDEX
    Explanations

    like or resembling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     %><%=
    0.48
    ...).
    0.37
     Harmony
    0.37
    雳
    0.36
    เดิม
    0.36
     verdes
    0.35
    வான்
    0.35
    }^{+}(
    0.35
    ่วย
    0.35
    心の
    0.35
    POSITIVE LOGITS
     resembling
    1.05
     마치
    1.05
     resemble
    1.01
     resembles
    1.01
     resemblance
    0.99
     resembled
    0.96
     ressembl
    0.96
     quasi
    0.95
    quasi
    0.92
    まるで
    0.92
    Act Density 0.110%

    No Known Activations