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

    Neuronpedia

    INDEX
    Explanations

    response type identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🐊
    0.37
     retirar
    0.36
     prema
    0.34
    儘
    0.34
     وحتى
    0.34
     أكبر
    0.34
     മികച്ച
    0.34
     karst
    0.34
     Tenggara
    0.34
     bele
    0.33
    POSITIVE LOGITS
    RO
    0.62
    Ri
    0.61
    RR
    0.59
    RA
    0.53
    RN
    0.52
    RW
    0.52
    RS
    0.51
    RF
    0.51
     RG
    0.51
    RY
    0.50
    Act Density 0.094%

    No Known Activations