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

    Neuronpedia

    INDEX
    Explanations

    dial 111

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cliff
    0.41
     Anth
    0.38
    cliff
    0.38
    abt
    0.38
    andel
    0.37
    Anth
    0.37
     Arden
    0.36
     Arvind
    0.35
    wso
    0.35
    getCql
    0.35
    POSITIVE LOGITS
     Bu
    0.43
     Interfaces
    0.39
     დ
    0.38
     տ
    0.36
    Bu
    0.36
     бро
    0.36
    ผ
    0.36
     interfaces
    0.36
    agoza
    0.36
     දු
    0.35
    Act Density 0.005%

    No Known Activations