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

    Neuronpedia

    INDEX
    Explanations

    math subjects

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Different
    0.50
    Different
    0.47
     DIFFERENT
    0.44
     пре
    0.41
     pre
    0.40
    Pre
    0.40
    预
    0.40
    different
    0.40
     不同
    0.40
    不同
    0.39
    POSITIVE LOGITS
     ihre
    0.41
     PH
    0.41
    Edu
    0.40
     AMI
    0.39
     Probab
    0.39
    SAP
    0.39
     deras
    0.38
     SEP
    0.38
     Abi
    0.38
     educational
    0.38
    Act Density 0.000%

    No Known Activations